Solar GGUF models
495 GGUF models in the Solar family, quantized by 58 uploaders. Sizes run from 406M to 250B parameters. The longest trained context is 1024K tokens.
About the Solar GGUF models
Solar is represented on ggufmodels.com by 495 GGUF models, quantized by 58 uploaders on Hugging Face. The most downloaded are Models Upstage Solar Pro Preview Instruct, Solar Open2 250B Mixed Quant and SOLAR 10.7B Instruct v1.0 uncensored. Parameter counts run from 406M to 250B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Solar model is between 0.3 to 62.3 GB, which is the quant most people start with. Most files come from mradermacher (164), tensorblock (109) and RichardErkhov (80). The quants you will meet most often are Q2_K (439), Q3_K_M (367), Q4_K_M (347) and Q5_K_M (335), where the number is how many models offer that quant.
Frequently asked questions
Which Solar GGUF should I download?
The most downloaded Solar GGUF here is Models Upstage Solar Pro Preview Instruct. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Solar model need?
Q4_K_M files of Solar models on this site range from 0.3 to 62.3 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Solar GGUF files come from?
The most common quantizers here are mradermacher, tensorblock and RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.